Design and Implementation of an IoT-Based Air Quality Monitoring and Early Warning System for Forest Fire Smoke Pollution Using MQ-135 Sensors
TL;DR
These findings demonstrate that the proposed system provides a reliable, energy-efficient, and sustainable solution for autonomous real-time air quality monitoring and early warning applications in remote forest environments, supporting rapid disaster response and environmental surveillance.
Abstract
Forest fires are a major source of air pollution, releasing hazardous gases and particulate matter that threaten environmental sustainability and public health. However, continuous air quality monitoring and early detection of forest fire smoke in remote and off-grid areas remain challenging due to the lack of re-liable electrical infrastructure and autonomous real-time monitoring systems. Therefore, this study aims to design, implement, and evaluate a solar-powered Internet of Things (IoT) based air quality monitoring and early warning system for forest fire smoke detection using an MQ-135 gas sensor. The proposed sys-tem integrates a 50 Wp photovoltaic panel, a Maximum Power Point Tracking (MPPT) charge controller, a 12 V 10 Ah battery, an Arduino Uno, an ESP32 communication module, and a cloud-based monitoring platform to enable autonomous and real-time operation. Experimental results demonstrated that the sys-tem successfully monitored CO₂ concentrations ranging from 415 ppm to 3600 ppm and transmitted meas-urement data to the IoT platform without observable transmission errors. Regression analysis between local LCD measurements and cloud-based data produced an R² value of 1.000 and a Mean Absolute Error (MAE) of 0 ppm, indicating perfect measurement consistency. The average communication delay was 620 ms, confirming the real-time capability of the proposed architecture. Furthermore, the threshold-based early warning mechanism achieved 100% accuracy, precision, recall, and F1-score in distinguishing safe and hazardous air quality conditions. Energy analysis revealed a total system power consumption of 2.15 W and an estimated autonomous operating duration of 55.8 hours. These findings demonstrate that the proposed system provides a reliable, energy-efficient, and sustainable solution for autonomous real-time air quality monitoring and early warning applications in remote forest environments, supporting rapid disaster response and environmental surveillance.